@inproceedings{kose-etal-2026-ragturk,
    title = "{RAGT}urk: Best Practices for Retrieval Augmented Generation in {T}urkish",
    author = {K{\"o}se, S{\"u}ha Ka{\u{g}}an  and
      Baytekin, Mehmet Can  and
      Akta{\c{s}}, Burak  and
      G{\"o}r{\"u}r, Bilge Kaan  and
      Munis, Evren Ayberk  and
      Y{\i}lmaz, Deniz  and
      Kartal, Muhammed Yusuf  and
      Toraman, Cagri},
    editor = {Oflazer, Kemal  and
      K{\"o}ksal, Abdullatif  and
      Varol, Onur},
    booktitle = "Proceedings of the Second Workshop Natural Language Processing for {T}urkic Languages ({SIGTURK} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.sigturk-1.15/",
    pages = "179--196",
    ISBN = "979-8-89176-370-8",
    abstract = "Retrieval-Augmented Generation (RAG) enhances LLM factuality, yet design guidance remains English-centric, limiting insights for morphologically rich languages like Turkish. We address this by constructing a comprehensive Turkish RAG dataset derived from Turkish Wikipedia and CulturaX, comprising question-answer pairs and relevant passage chunks. We benchmark seven stages of the RAG pipeline{---}from query transformation and reranking to answer refinement{---}without task-specific fine-tuning. Our results show that complex methods like HyDE maximize accuracy (85{\%}) that is considerably higher than the baseline (78.70{\%}). Also a Pareto-optimal configuration using Cross-encoder Reranking and Context Augmentation achieves comparable performance (84.60{\%}) with much lower cost. We further demonstrate that over-stacking generative modules can degrade performance by distorting morphological cues, whereas simple query clarification with robust reranking offers an effective solution."
}